© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57041
    Prev
    Next
    INDEX
    Explanations

    punctuation or quotes used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teg
    -0.07
     Fus
    -0.06
    ARING
    -0.06
     ìļ
    -0.06
    oningen
    -0.06
    ofi
    -0.06
     graz
    -0.06
    ubb
    -0.06
    bout
    -0.06
    afi
    -0.06
    POSITIVE LOGITS
    \Collections
    0.07
    _DECL
    0.06
     pools
    0.06
     ucwords
    0.06
     gezocht
    0.06
    кÑĥлÑı
    0.06
    ller
    0.06
     Hra
    0.06
    znám
    0.06
    менÑĪ
    0.06
    Activations Density 0.001%

    No Known Activations